© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 5823
    Prev
    Next
    INDEX
    Explanations

    information related to different types or forms of creative works, specifically in theater and drama

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    >window
    -0.06
    ichen
    -0.06
     sobie
    -0.06
    ç£
    -0.06
    sets
    -0.06
    br
    -0.06
    omor
    -0.05
     victim
    -0.05
    íķĺìĭł
    -0.05
    acket
    -0.05
    POSITIVE LOGITS
     types
    0.16
     type
    0.16
    ç±»åŀĭ
    0.15
    type
    0.13
    types
    0.13
    -types
    0.13
     ÑĤипа
    0.12
     Types
    0.12
     tipo
    0.12
    åŀĭ
    0.11
    Activations Density 0.075%

    No Known Activations